Save the date! Google I/O returns May 18-20 Register now

Agents is a library for reinforcement learning in TensorFlow.

import tensorflow as tf
from tf_agents.networks import q_network
from tf_agents.agents.dqn import dqn_agent

q_net = q_network.QNetwork(
  train_env.observation_spec(),
  train_env.action_spec(),
  fc_layer_params=(100,))

agent = dqn_agent.DqnAgent(
  train_env.time_step_spec(),
  train_env.action_spec(),
  q_network=q_net,
  optimizer=optimizer,
  td_errors_loss_fn=common.element_wise_squared_loss,
  train_step_counter=tf.Variable(0))

agent.initialize()
TF-Agents makes designing, implementing and testing new RL algorithms easier, by providing well tested modular components that can be modified and extended. It enables fast code iteration, with good test integration and benchmarking.